A5024322166- Biomedical Text Mining and Ontologies
- Topic Modeling
- Natural Language Processing Techniques
- Semantic Web and Ontologies
- Advanced Text Analysis Techniques
- Machine Learning in Healthcare
Mid Cheshire Hospitals NHS Foundation Trust
2018-2021
NHS England
2017-2020
Automatic identification of term variants or acceptable alternative free-text terms for gene and protein names from the millions biomedical publications is a challenging task. Ontologies, such as Cardiovascular Disease Ontology (CVDO), capture domain knowledge in computational form can provide context gene/protein written literature. This study investigates: 1) if word embeddings Deep Learning algorithms list given interest; 2) biological CVDO improve without modifying created. We have...
We investigate the application of distributional semantics models for facilitating unsupervised extraction biomedical terms from unannotated corpora. Term is used as first step an ontology learning process that aims to (semi-)automatic annotation concepts and relations more than 300K PubMed titles abstracts. experimented with both traditional methods such Latent Semantic Analysis (LSA) Dirichlet Allocation (LDA) well neural language CBOW Skip-gram Deep Learning. The evaluation conducted...
How to treat a disease remains be the most common type of clinical question. Obtaining evidence-based answers from biomedical literature is difficult. Analogical reasoning with embeddings deep learning (embedding analogies) may extract such facts, although state-of-the-art focuses on pair-based proportional (pairwise) analogies as man:woman::king:queen ("queen = -man +king +woman").
<sec> <title>BACKGROUND</title> How to treat a disease remains be the most common type of clinical question. Obtaining evidence-based answers from biomedical literature is difficult. Analogical reasoning with embeddings deep learning (embedding analogies) may extract such facts, although state-of-the-art focuses on pair-based proportional (pairwise) analogies as man:woman::king:queen (“<i>queen = −man +king +woman</i>”). </sec> <title>OBJECTIVE</title> This study aimed...